AI Paper Atlas

Research map / Learning theory and algorithms / Clustering

How to tell when a clustering is (approximately) correct using convex relaxations

Marina Meila

NeurIPS 2018 · Learning theory and algorithms › Clustering · approach: Clustering approximation algorithms · 6 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
remove 60% of points closest to centers instead of outlier removalSDP BTR bound · aspirin MD K=2BTR bound epsilon: .065 -> 0.047Hurt
remove 60% of points closest to centers instead of outlier removalSDP BTR bound · aspirin MD K=2run time: 10h -> 42 minutesImproved
increase dispersion sigma from 0.6 to 1.2 (ablation)SDP BTR bound · K=4 unequal normal, n=200BTR bound epsilon: 0.00(0.00) -> 0.28 (0.08)Hurt
increase n from 200 to 800 (ablation)SDP BTR bound · K=4 unequal normal, sigma=1.2BTR bound epsilon: 0.28 (0.08) -> 0.21 (0.03)No clear effect
use non-normal instead of normal clustersSDP BTR bound · K=4 sigma=1.2, n=200BTR bound epsilon: 0.28 (0.08) -> 0.16 (0.06)Improved
use SDP bound instead of spectral boundspectral bound · K=4, n=1024bound tightnessImproved
place K=6 cluster centers along a linespectral bound · K=6 clustersbound qualityHurt
decrease smallest cluster proportion p_min (ablation)SDP BTR bound · unequal cluster sizesBTR bound epsilonHurt
unequal vs equal cluster sizesSDP BTR bound · K=4BTR bound epsilonNo clear effect

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy